Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     국내
    -0.07
    仰
    -0.07
    Cou
    -0.06
    Ent
    -0.06
     italiane
    -0.06
     cruc
    -0.06
    弱
    -0.06
     مط
    -0.06
    提高
    -0.06
    Ч
    -0.06
    POSITIVE LOGITS
     provinces
    0.08
    .Matrix
    0.07
     Eastern
    0.07
    legates
    0.07
    	Returns
    0.07
     Reactive
    0.06
    ointed
    0.06
    Recipient
    0.06
    .Department
    0.06
    (stream
    0.06
    Act Density 0.001%

    No Known Activations